config.json

{
  "architectures": [
    "HfMoondream"
  ],
  "auto_map": {
    "AutoConfig": "hf_moondream.HfConfig",
    "AutoModelForCausalLM": "hf_moondream.HfMoondream"
  },
  "config": {
    "skills": [
      "query",
      "caption",
      "detect",
      "point"
    ]
  },
  "model_type": "moondream3",
  "quantization": {
    "group_size": 64,
    "bits": 8,
    "mode": "affine"
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 8,
    "mode": "affine"
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.1"
}